Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    INDEX
    Explanations

    Code

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    (void
    -0.07
    hours
    -0.06
    -google
    -0.06
     Entries
    -0.06
    %'
    -0.06
    (`
    -0.06
    “One
    -0.06
     Agree
    -0.06
    _MARK
    -0.06
     widths
    -0.06
    POSITIVE LOGITS
     घटन
    0.07
     Kar
    0.07
     पक
    0.06
     traged
    0.06
     hacking
    0.06
     бал
    0.06
    ظٹط
    0.06
     Đồng
    0.06
     cerr
    0.06
     bgcolor
    0.06
    Act Density 0.010%

    No Known Activations